Upload checkpoint and eval results at step 3500
Browse files- checkpoint-3500/config.json +38 -0
- checkpoint-3500/eval_results.json +12 -0
- checkpoint-3500/eval_step_003500.json +16 -0
- checkpoint-3500/model.safetensors +3 -0
- checkpoint-3500/optimizer.pt +3 -0
- checkpoint-3500/rng_state.pth +3 -0
- checkpoint-3500/scaler.pt +3 -0
- checkpoint-3500/scheduler.pt +3 -0
- checkpoint-3500/tokenizer.json +0 -0
- checkpoint-3500/tokenizer_config.json +15 -0
- checkpoint-3500/trainer_state.json +1114 -0
- checkpoint-3500/training_args.bin +3 -0
checkpoint-3500/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "benign",
|
| 17 |
+
"1": "malicious"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"is_decoder": false,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"benign": 0,
|
| 24 |
+
"malicious": 1
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 512,
|
| 28 |
+
"model_type": "bert",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 0,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"tie_word_embeddings": true,
|
| 34 |
+
"transformers_version": "5.12.1",
|
| 35 |
+
"type_vocab_size": 2,
|
| 36 |
+
"use_cache": false,
|
| 37 |
+
"vocab_size": 30522
|
| 38 |
+
}
|
checkpoint-3500/eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 3500,
|
| 3 |
+
"epoch": 2.831715210355987,
|
| 4 |
+
"time": "2026-06-26 22:48:00",
|
| 5 |
+
"metrics": {
|
| 6 |
+
"eval_loss": 0.1581990271806717,
|
| 7 |
+
"eval_accuracy": 0.9676604345629105,
|
| 8 |
+
"eval_precision": 0.9718954248366013,
|
| 9 |
+
"eval_recall": 0.9860742705570292,
|
| 10 |
+
"eval_f1": 0.9789335088874259
|
| 11 |
+
}
|
| 12 |
+
}
|
checkpoint-3500/eval_step_003500.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 3500,
|
| 3 |
+
"epoch": 2.831715210355987,
|
| 4 |
+
"time": "2026-06-26 22:48:00",
|
| 5 |
+
"metrics": {
|
| 6 |
+
"eval_loss": 0.1581990271806717,
|
| 7 |
+
"eval_accuracy": 0.9676604345629105,
|
| 8 |
+
"eval_precision": 0.9718954248366013,
|
| 9 |
+
"eval_recall": 0.9860742705570292,
|
| 10 |
+
"eval_f1": 0.9789335088874259,
|
| 11 |
+
"eval_runtime": 34.2504,
|
| 12 |
+
"eval_samples_per_second": 57.78,
|
| 13 |
+
"eval_steps_per_second": 3.62,
|
| 14 |
+
"epoch": 2.831715210355987
|
| 15 |
+
}
|
| 16 |
+
}
|
checkpoint-3500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9581fd443e218b770477db9fea4eebcaa1d51c1542792f3603d9c7b2b4ebca23
|
| 3 |
+
size 437958624
|
checkpoint-3500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e49643f03c1cd14315908fb8099a4a82994bfa948894f9c054fbc552fe0ca97
|
| 3 |
+
size 876041611
|
checkpoint-3500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a502a5a86e198b70b9e3f3adf4f43fae0d2b9e246f1f384ef9d53dbec1560d3
|
| 3 |
+
size 14645
|
checkpoint-3500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac1b9358ab1cb9acff90f4d1d692ac08bbdb1986a66544aed9f6fe9b801b17b3
|
| 3 |
+
size 1383
|
checkpoint-3500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:935e7fb4649ad74c00f1fa3751f08b20d79beb9d2f313ae17514c7da448b90a6
|
| 3 |
+
size 1465
|
checkpoint-3500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 1000000000,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
checkpoint-3500/trainer_state.json
ADDED
|
@@ -0,0 +1,1114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 3500,
|
| 3 |
+
"best_metric": 0.9789335088874259,
|
| 4 |
+
"best_model_checkpoint": "/kaggle/working/outputs/bert_rd_keystrokes/checkpoint-3500",
|
| 5 |
+
"epoch": 2.831715210355987,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0008090614886731392,
|
| 14 |
+
"grad_norm": 2.5394184589385986,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 0.6913009285926819,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.020226537216828478,
|
| 21 |
+
"grad_norm": 3.3882575035095215,
|
| 22 |
+
"learning_rate": 9.716599190283402e-07,
|
| 23 |
+
"loss": 0.710881233215332,
|
| 24 |
+
"step": 25
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.040453074433656956,
|
| 28 |
+
"grad_norm": 4.59527063369751,
|
| 29 |
+
"learning_rate": 1.9838056680161946e-06,
|
| 30 |
+
"loss": 0.6965625762939454,
|
| 31 |
+
"step": 50
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.06067961165048544,
|
| 35 |
+
"grad_norm": 6.466946125030518,
|
| 36 |
+
"learning_rate": 2.995951417004049e-06,
|
| 37 |
+
"loss": 0.6713954925537109,
|
| 38 |
+
"step": 75
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08090614886731391,
|
| 42 |
+
"grad_norm": 5.92415714263916,
|
| 43 |
+
"learning_rate": 4.008097165991903e-06,
|
| 44 |
+
"loss": 0.6306858444213868,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1011326860841424,
|
| 49 |
+
"grad_norm": 7.790467262268066,
|
| 50 |
+
"learning_rate": 5.020242914979757e-06,
|
| 51 |
+
"loss": 0.5511775207519531,
|
| 52 |
+
"step": 125
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12135922330097088,
|
| 56 |
+
"grad_norm": 5.874857425689697,
|
| 57 |
+
"learning_rate": 6.0323886639676124e-06,
|
| 58 |
+
"loss": 0.5026376342773438,
|
| 59 |
+
"step": 150
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14158576051779936,
|
| 63 |
+
"grad_norm": 12.701870918273926,
|
| 64 |
+
"learning_rate": 7.044534412955466e-06,
|
| 65 |
+
"loss": 0.4295468521118164,
|
| 66 |
+
"step": 175
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.16181229773462782,
|
| 70 |
+
"grad_norm": 5.137658596038818,
|
| 71 |
+
"learning_rate": 8.056680161943322e-06,
|
| 72 |
+
"loss": 0.3788005828857422,
|
| 73 |
+
"step": 200
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1820388349514563,
|
| 77 |
+
"grad_norm": 5.249273300170898,
|
| 78 |
+
"learning_rate": 9.068825910931175e-06,
|
| 79 |
+
"loss": 0.2651861381530762,
|
| 80 |
+
"step": 225
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2022653721682848,
|
| 84 |
+
"grad_norm": 38.753013610839844,
|
| 85 |
+
"learning_rate": 1.008097165991903e-05,
|
| 86 |
+
"loss": 0.3065790557861328,
|
| 87 |
+
"step": 250
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.22249190938511326,
|
| 91 |
+
"grad_norm": 13.836112022399902,
|
| 92 |
+
"learning_rate": 1.1093117408906884e-05,
|
| 93 |
+
"loss": 0.38094028472900393,
|
| 94 |
+
"step": 275
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.24271844660194175,
|
| 98 |
+
"grad_norm": 6.559873580932617,
|
| 99 |
+
"learning_rate": 1.2105263157894737e-05,
|
| 100 |
+
"loss": 0.3118729019165039,
|
| 101 |
+
"step": 300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.26294498381877024,
|
| 105 |
+
"grad_norm": 7.356478214263916,
|
| 106 |
+
"learning_rate": 1.3117408906882592e-05,
|
| 107 |
+
"loss": 0.23761932373046876,
|
| 108 |
+
"step": 325
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.28317152103559873,
|
| 112 |
+
"grad_norm": 4.0845184326171875,
|
| 113 |
+
"learning_rate": 1.4129554655870446e-05,
|
| 114 |
+
"loss": 0.26587358474731443,
|
| 115 |
+
"step": 350
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.30339805825242716,
|
| 119 |
+
"grad_norm": 28.685104370117188,
|
| 120 |
+
"learning_rate": 1.5141700404858302e-05,
|
| 121 |
+
"loss": 0.3239314651489258,
|
| 122 |
+
"step": 375
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.32362459546925565,
|
| 126 |
+
"grad_norm": 1.7896462678909302,
|
| 127 |
+
"learning_rate": 1.6153846153846154e-05,
|
| 128 |
+
"loss": 0.24046634674072265,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.34385113268608414,
|
| 133 |
+
"grad_norm": 6.960549831390381,
|
| 134 |
+
"learning_rate": 1.716599190283401e-05,
|
| 135 |
+
"loss": 0.27144105911254884,
|
| 136 |
+
"step": 425
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3640776699029126,
|
| 140 |
+
"grad_norm": 22.062820434570312,
|
| 141 |
+
"learning_rate": 1.8178137651821864e-05,
|
| 142 |
+
"loss": 0.24825719833374024,
|
| 143 |
+
"step": 450
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3843042071197411,
|
| 147 |
+
"grad_norm": 0.4285735785961151,
|
| 148 |
+
"learning_rate": 1.9190283400809718e-05,
|
| 149 |
+
"loss": 0.22249792098999024,
|
| 150 |
+
"step": 475
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.4045307443365696,
|
| 154 |
+
"grad_norm": 0.26966607570648193,
|
| 155 |
+
"learning_rate": 1.999993769982229e-05,
|
| 156 |
+
"loss": 0.25503772735595703,
|
| 157 |
+
"step": 500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4045307443365696,
|
| 161 |
+
"eval_accuracy": 0.9550277918140475,
|
| 162 |
+
"eval_f1": 0.9709055246812683,
|
| 163 |
+
"eval_loss": 0.1790667176246643,
|
| 164 |
+
"eval_precision": 0.9574468085106383,
|
| 165 |
+
"eval_recall": 0.9847480106100795,
|
| 166 |
+
"eval_runtime": 34.5481,
|
| 167 |
+
"eval_samples_per_second": 57.282,
|
| 168 |
+
"eval_steps_per_second": 3.589,
|
| 169 |
+
"step": 500
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.42475728155339804,
|
| 173 |
+
"grad_norm": 1.232269048690796,
|
| 174 |
+
"learning_rate": 1.9997757275108847e-05,
|
| 175 |
+
"loss": 0.2667963790893555,
|
| 176 |
+
"step": 525
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.4449838187702265,
|
| 180 |
+
"grad_norm": 12.561880111694336,
|
| 181 |
+
"learning_rate": 1.9992462617728763e-05,
|
| 182 |
+
"loss": 0.2216647148132324,
|
| 183 |
+
"step": 550
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.465210355987055,
|
| 187 |
+
"grad_norm": 0.4093881845474243,
|
| 188 |
+
"learning_rate": 1.9984055376931414e-05,
|
| 189 |
+
"loss": 0.23123834609985353,
|
| 190 |
+
"step": 575
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.4854368932038835,
|
| 194 |
+
"grad_norm": 3.573305368423462,
|
| 195 |
+
"learning_rate": 1.9972538171514525e-05,
|
| 196 |
+
"loss": 0.2226162338256836,
|
| 197 |
+
"step": 600
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.5056634304207119,
|
| 201 |
+
"grad_norm": 12.511730194091797,
|
| 202 |
+
"learning_rate": 1.9957914589008405e-05,
|
| 203 |
+
"loss": 0.2451229476928711,
|
| 204 |
+
"step": 625
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.5258899676375405,
|
| 208 |
+
"grad_norm": 11.676703453063965,
|
| 209 |
+
"learning_rate": 1.9940189184558487e-05,
|
| 210 |
+
"loss": 0.25127721786499024,
|
| 211 |
+
"step": 650
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.5461165048543689,
|
| 215 |
+
"grad_norm": 5.444802284240723,
|
| 216 |
+
"learning_rate": 1.9919367479506413e-05,
|
| 217 |
+
"loss": 0.30009620666503906,
|
| 218 |
+
"step": 675
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.5663430420711975,
|
| 222 |
+
"grad_norm": 1.9753400087356567,
|
| 223 |
+
"learning_rate": 1.989545595967018e-05,
|
| 224 |
+
"loss": 0.3415143585205078,
|
| 225 |
+
"step": 700
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.5865695792880259,
|
| 229 |
+
"grad_norm": 0.7816814184188843,
|
| 230 |
+
"learning_rate": 1.986846207332384e-05,
|
| 231 |
+
"loss": 0.24259204864501954,
|
| 232 |
+
"step": 725
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.6067961165048543,
|
| 236 |
+
"grad_norm": 20.42180061340332,
|
| 237 |
+
"learning_rate": 1.9838394228877443e-05,
|
| 238 |
+
"loss": 0.1343485450744629,
|
| 239 |
+
"step": 750
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.6270226537216829,
|
| 243 |
+
"grad_norm": 21.677453994750977,
|
| 244 |
+
"learning_rate": 1.980526179225785e-05,
|
| 245 |
+
"loss": 0.25507625579833987,
|
| 246 |
+
"step": 775
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.6472491909385113,
|
| 250 |
+
"grad_norm": 4.561895370483398,
|
| 251 |
+
"learning_rate": 1.97690750839913e-05,
|
| 252 |
+
"loss": 0.26329845428466797,
|
| 253 |
+
"step": 800
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.6674757281553398,
|
| 257 |
+
"grad_norm": 0.17717082798480988,
|
| 258 |
+
"learning_rate": 1.9729845375988694e-05,
|
| 259 |
+
"loss": 0.16668357849121093,
|
| 260 |
+
"step": 825
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.6877022653721683,
|
| 264 |
+
"grad_norm": 6.059898853302002,
|
| 265 |
+
"learning_rate": 1.968758488803439e-05,
|
| 266 |
+
"loss": 0.2621467399597168,
|
| 267 |
+
"step": 850
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.7079288025889967,
|
| 271 |
+
"grad_norm": 5.8439130783081055,
|
| 272 |
+
"learning_rate": 1.9642306783979902e-05,
|
| 273 |
+
"loss": 0.3152758979797363,
|
| 274 |
+
"step": 875
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.7281553398058253,
|
| 278 |
+
"grad_norm": 5.4012041091918945,
|
| 279 |
+
"learning_rate": 1.959402516764339e-05,
|
| 280 |
+
"loss": 0.2474656867980957,
|
| 281 |
+
"step": 900
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.7483818770226537,
|
| 285 |
+
"grad_norm": 13.964224815368652,
|
| 286 |
+
"learning_rate": 1.954275507841646e-05,
|
| 287 |
+
"loss": 0.22230056762695313,
|
| 288 |
+
"step": 925
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.7686084142394822,
|
| 292 |
+
"grad_norm": 8.115334510803223,
|
| 293 |
+
"learning_rate": 1.948851248657947e-05,
|
| 294 |
+
"loss": 0.3234273910522461,
|
| 295 |
+
"step": 950
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.7888349514563107,
|
| 299 |
+
"grad_norm": 0.23621903359889984,
|
| 300 |
+
"learning_rate": 1.9431314288326925e-05,
|
| 301 |
+
"loss": 0.1469671630859375,
|
| 302 |
+
"step": 975
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.8090614886731392,
|
| 306 |
+
"grad_norm": 3.0084638595581055,
|
| 307 |
+
"learning_rate": 1.9371178300504394e-05,
|
| 308 |
+
"loss": 0.24907604217529297,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.8090614886731392,
|
| 313 |
+
"eval_accuracy": 0.9615967660434563,
|
| 314 |
+
"eval_f1": 0.9752604166666666,
|
| 315 |
+
"eval_loss": 0.15361516177654266,
|
| 316 |
+
"eval_precision": 0.9578005115089514,
|
| 317 |
+
"eval_recall": 0.993368700265252,
|
| 318 |
+
"eval_runtime": 34.2684,
|
| 319 |
+
"eval_samples_per_second": 57.75,
|
| 320 |
+
"eval_steps_per_second": 3.618,
|
| 321 |
+
"step": 1000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.8292880258899676,
|
| 325 |
+
"grad_norm": 0.658998429775238,
|
| 326 |
+
"learning_rate": 1.930812325505871e-05,
|
| 327 |
+
"loss": 0.128564510345459,
|
| 328 |
+
"step": 1025
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.8495145631067961,
|
| 332 |
+
"grad_norm": 14.597765922546387,
|
| 333 |
+
"learning_rate": 1.9242168793203088e-05,
|
| 334 |
+
"loss": 0.28263355255126954,
|
| 335 |
+
"step": 1050
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.8697411003236246,
|
| 339 |
+
"grad_norm": 10.520459175109863,
|
| 340 |
+
"learning_rate": 1.9173335459299025e-05,
|
| 341 |
+
"loss": 0.20550737380981446,
|
| 342 |
+
"step": 1075
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.889967637540453,
|
| 346 |
+
"grad_norm": 8.196412086486816,
|
| 347 |
+
"learning_rate": 1.9101644694456873e-05,
|
| 348 |
+
"loss": 0.21728286743164063,
|
| 349 |
+
"step": 1100
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.9101941747572816,
|
| 353 |
+
"grad_norm": 10.451470375061035,
|
| 354 |
+
"learning_rate": 1.902711882985708e-05,
|
| 355 |
+
"loss": 0.22805599212646485,
|
| 356 |
+
"step": 1125
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.93042071197411,
|
| 360 |
+
"grad_norm": 0.7729430794715881,
|
| 361 |
+
"learning_rate": 1.894978107979417e-05,
|
| 362 |
+
"loss": 0.19682933807373046,
|
| 363 |
+
"step": 1150
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.9506472491909385,
|
| 367 |
+
"grad_norm": 1.208465814590454,
|
| 368 |
+
"learning_rate": 1.886965553444568e-05,
|
| 369 |
+
"loss": 0.21496267318725587,
|
| 370 |
+
"step": 1175
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.970873786407767,
|
| 374 |
+
"grad_norm": 8.930377006530762,
|
| 375 |
+
"learning_rate": 1.8786767152368197e-05,
|
| 376 |
+
"loss": 0.2545662498474121,
|
| 377 |
+
"step": 1200
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.9911003236245954,
|
| 381 |
+
"grad_norm": 8.784140586853027,
|
| 382 |
+
"learning_rate": 1.8701141752722966e-05,
|
| 383 |
+
"loss": 0.15711795806884765,
|
| 384 |
+
"step": 1225
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.0113268608414239,
|
| 388 |
+
"grad_norm": 6.048089504241943,
|
| 389 |
+
"learning_rate": 1.8612806007233382e-05,
|
| 390 |
+
"loss": 0.18027606964111328,
|
| 391 |
+
"step": 1250
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.0315533980582525,
|
| 395 |
+
"grad_norm": 2.1826491355895996,
|
| 396 |
+
"learning_rate": 1.8521787431876954e-05,
|
| 397 |
+
"loss": 0.1467225170135498,
|
| 398 |
+
"step": 1275
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.051779935275081,
|
| 402 |
+
"grad_norm": 13.113622665405273,
|
| 403 |
+
"learning_rate": 1.8428114378314237e-05,
|
| 404 |
+
"loss": 0.21480131149291992,
|
| 405 |
+
"step": 1300
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.0720064724919094,
|
| 409 |
+
"grad_norm": 6.212342262268066,
|
| 410 |
+
"learning_rate": 1.8331816025057508e-05,
|
| 411 |
+
"loss": 0.22947580337524415,
|
| 412 |
+
"step": 1325
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.0922330097087378,
|
| 416 |
+
"grad_norm": 0.22277741134166718,
|
| 417 |
+
"learning_rate": 1.823292236838186e-05,
|
| 418 |
+
"loss": 0.10173338890075684,
|
| 419 |
+
"step": 1350
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.1124595469255663,
|
| 423 |
+
"grad_norm": 11.058046340942383,
|
| 424 |
+
"learning_rate": 1.813146421298154e-05,
|
| 425 |
+
"loss": 0.2582175064086914,
|
| 426 |
+
"step": 1375
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.132686084142395,
|
| 430 |
+
"grad_norm": 9.502155303955078,
|
| 431 |
+
"learning_rate": 1.802747316237454e-05,
|
| 432 |
+
"loss": 0.23467300415039063,
|
| 433 |
+
"step": 1400
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.1529126213592233,
|
| 437 |
+
"grad_norm": 5.091904640197754,
|
| 438 |
+
"learning_rate": 1.792098160905829e-05,
|
| 439 |
+
"loss": 0.18842180252075194,
|
| 440 |
+
"step": 1425
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.1731391585760518,
|
| 444 |
+
"grad_norm": 0.2650909721851349,
|
| 445 |
+
"learning_rate": 1.7812022724419624e-05,
|
| 446 |
+
"loss": 0.13545321464538573,
|
| 447 |
+
"step": 1450
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.1933656957928802,
|
| 451 |
+
"grad_norm": 3.7782185077667236,
|
| 452 |
+
"learning_rate": 1.7700630448402125e-05,
|
| 453 |
+
"loss": 0.16887168884277343,
|
| 454 |
+
"step": 1475
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.2135922330097086,
|
| 458 |
+
"grad_norm": 0.5704866051673889,
|
| 459 |
+
"learning_rate": 1.758683947893406e-05,
|
| 460 |
+
"loss": 0.22910015106201173,
|
| 461 |
+
"step": 1500
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.2135922330097086,
|
| 465 |
+
"eval_accuracy": 0.9605861546235472,
|
| 466 |
+
"eval_f1": 0.974559686888454,
|
| 467 |
+
"eval_loss": 0.14868734776973724,
|
| 468 |
+
"eval_precision": 0.9589216944801027,
|
| 469 |
+
"eval_recall": 0.9907161803713528,
|
| 470 |
+
"eval_runtime": 34.2705,
|
| 471 |
+
"eval_samples_per_second": 57.746,
|
| 472 |
+
"eval_steps_per_second": 3.618,
|
| 473 |
+
"step": 1500
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.2338187702265373,
|
| 477 |
+
"grad_norm": 16.6047306060791,
|
| 478 |
+
"learning_rate": 1.747068526112022e-05,
|
| 479 |
+
"loss": 0.14131352424621582,
|
| 480 |
+
"step": 1525
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.2540453074433657,
|
| 484 |
+
"grad_norm": 5.992398262023926,
|
| 485 |
+
"learning_rate": 1.735220397620101e-05,
|
| 486 |
+
"loss": 0.15291913986206054,
|
| 487 |
+
"step": 1550
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.2742718446601942,
|
| 491 |
+
"grad_norm": 0.36782047152519226,
|
| 492 |
+
"learning_rate": 1.7231432530282246e-05,
|
| 493 |
+
"loss": 0.09922373771667481,
|
| 494 |
+
"step": 1575
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.2944983818770226,
|
| 498 |
+
"grad_norm": 1.3172669410705566,
|
| 499 |
+
"learning_rate": 1.7108408542839146e-05,
|
| 500 |
+
"loss": 0.1941922378540039,
|
| 501 |
+
"step": 1600
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.3147249190938513,
|
| 505 |
+
"grad_norm": 0.693942666053772,
|
| 506 |
+
"learning_rate": 1.698317033499813e-05,
|
| 507 |
+
"loss": 0.16940629959106446,
|
| 508 |
+
"step": 1625
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.3349514563106797,
|
| 512 |
+
"grad_norm": 0.1476801335811615,
|
| 513 |
+
"learning_rate": 1.6855756917600057e-05,
|
| 514 |
+
"loss": 0.12692631721496583,
|
| 515 |
+
"step": 1650
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.3551779935275081,
|
| 519 |
+
"grad_norm": 23.20606231689453,
|
| 520 |
+
"learning_rate": 1.6726207979048604e-05,
|
| 521 |
+
"loss": 0.25180328369140625,
|
| 522 |
+
"step": 1675
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.3754045307443366,
|
| 526 |
+
"grad_norm": 0.3847394287586212,
|
| 527 |
+
"learning_rate": 1.6594563872947613e-05,
|
| 528 |
+
"loss": 0.13337421417236328,
|
| 529 |
+
"step": 1700
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.395631067961165,
|
| 533 |
+
"grad_norm": 7.629310131072998,
|
| 534 |
+
"learning_rate": 1.6460865605531214e-05,
|
| 535 |
+
"loss": 0.17984333038330078,
|
| 536 |
+
"step": 1725
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.4158576051779934,
|
| 540 |
+
"grad_norm": 0.40370574593544006,
|
| 541 |
+
"learning_rate": 1.6325154822890663e-05,
|
| 542 |
+
"loss": 0.15392546653747557,
|
| 543 |
+
"step": 1750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.436084142394822,
|
| 547 |
+
"grad_norm": 3.1435182094573975,
|
| 548 |
+
"learning_rate": 1.618747379800188e-05,
|
| 549 |
+
"loss": 0.1560378646850586,
|
| 550 |
+
"step": 1775
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.4563106796116505,
|
| 554 |
+
"grad_norm": 6.557313919067383,
|
| 555 |
+
"learning_rate": 1.6047865417557695e-05,
|
| 556 |
+
"loss": 0.23071422576904296,
|
| 557 |
+
"step": 1800
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.476537216828479,
|
| 561 |
+
"grad_norm": 4.851151943206787,
|
| 562 |
+
"learning_rate": 1.5906373168608952e-05,
|
| 563 |
+
"loss": 0.17919015884399414,
|
| 564 |
+
"step": 1825
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.4967637540453074,
|
| 568 |
+
"grad_norm": 6.987358093261719,
|
| 569 |
+
"learning_rate": 1.576304112501858e-05,
|
| 570 |
+
"loss": 0.22098312377929688,
|
| 571 |
+
"step": 1850
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.516990291262136,
|
| 575 |
+
"grad_norm": 4.638033390045166,
|
| 576 |
+
"learning_rate": 1.5617913933732892e-05,
|
| 577 |
+
"loss": 0.1659644889831543,
|
| 578 |
+
"step": 1875
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.5372168284789645,
|
| 582 |
+
"grad_norm": 3.2221922874450684,
|
| 583 |
+
"learning_rate": 1.5471036800874375e-05,
|
| 584 |
+
"loss": 0.18479549407958984,
|
| 585 |
+
"step": 1900
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.557443365695793,
|
| 589 |
+
"grad_norm": 0.3064526617527008,
|
| 590 |
+
"learning_rate": 1.5322455477660274e-05,
|
| 591 |
+
"loss": 0.18851667404174804,
|
| 592 |
+
"step": 1925
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.5776699029126213,
|
| 596 |
+
"grad_norm": 15.610395431518555,
|
| 597 |
+
"learning_rate": 1.5172216246151426e-05,
|
| 598 |
+
"loss": 0.23035451889038086,
|
| 599 |
+
"step": 1950
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.5978964401294498,
|
| 603 |
+
"grad_norm": 8.045638084411621,
|
| 604 |
+
"learning_rate": 1.50203659048357e-05,
|
| 605 |
+
"loss": 0.05388895988464355,
|
| 606 |
+
"step": 1975
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 1.6181229773462782,
|
| 610 |
+
"grad_norm": 12.035682678222656,
|
| 611 |
+
"learning_rate": 1.4866951754050605e-05,
|
| 612 |
+
"loss": 0.2584081268310547,
|
| 613 |
+
"step": 2000
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 1.6181229773462782,
|
| 617 |
+
"eval_accuracy": 0.9621020717534108,
|
| 618 |
+
"eval_f1": 0.9754661432777233,
|
| 619 |
+
"eval_loss": 0.145921990275383,
|
| 620 |
+
"eval_precision": 0.9625564880568108,
|
| 621 |
+
"eval_recall": 0.9887267904509284,
|
| 622 |
+
"eval_runtime": 34.2514,
|
| 623 |
+
"eval_samples_per_second": 57.779,
|
| 624 |
+
"eval_steps_per_second": 3.62,
|
| 625 |
+
"step": 2000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.6383495145631068,
|
| 629 |
+
"grad_norm": 11.77345085144043,
|
| 630 |
+
"learning_rate": 1.4712021581249534e-05,
|
| 631 |
+
"loss": 0.17600563049316406,
|
| 632 |
+
"step": 2025
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.6585760517799353,
|
| 636 |
+
"grad_norm": 0.31589698791503906,
|
| 637 |
+
"learning_rate": 1.4555623646116325e-05,
|
| 638 |
+
"loss": 0.2075064277648926,
|
| 639 |
+
"step": 2050
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.6788025889967637,
|
| 643 |
+
"grad_norm": 6.368648529052734,
|
| 644 |
+
"learning_rate": 1.4397806665532693e-05,
|
| 645 |
+
"loss": 0.15077384948730468,
|
| 646 |
+
"step": 2075
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.6990291262135924,
|
| 650 |
+
"grad_norm": 0.19168436527252197,
|
| 651 |
+
"learning_rate": 1.4238619798403266e-05,
|
| 652 |
+
"loss": 0.21610870361328124,
|
| 653 |
+
"step": 2100
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.7192556634304208,
|
| 657 |
+
"grad_norm": 3.6846413612365723,
|
| 658 |
+
"learning_rate": 1.4078112630342891e-05,
|
| 659 |
+
"loss": 0.1896487808227539,
|
| 660 |
+
"step": 2125
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.7394822006472492,
|
| 664 |
+
"grad_norm": 6.122201919555664,
|
| 665 |
+
"learning_rate": 1.3916335158231101e-05,
|
| 666 |
+
"loss": 0.18662324905395508,
|
| 667 |
+
"step": 2150
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.7597087378640777,
|
| 671 |
+
"grad_norm": 8.101036071777344,
|
| 672 |
+
"learning_rate": 1.3753337774638397e-05,
|
| 673 |
+
"loss": 0.14516648292541504,
|
| 674 |
+
"step": 2175
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.779935275080906,
|
| 678 |
+
"grad_norm": 0.39058423042297363,
|
| 679 |
+
"learning_rate": 1.3589171252129329e-05,
|
| 680 |
+
"loss": 0.23894359588623046,
|
| 681 |
+
"step": 2200
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.8001618122977345,
|
| 685 |
+
"grad_norm": 20.84650993347168,
|
| 686 |
+
"learning_rate": 1.3423886727447176e-05,
|
| 687 |
+
"loss": 0.16099306106567382,
|
| 688 |
+
"step": 2225
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.820388349514563,
|
| 692 |
+
"grad_norm": 2.713047504425049,
|
| 693 |
+
"learning_rate": 1.325753568558521e-05,
|
| 694 |
+
"loss": 0.23093647003173828,
|
| 695 |
+
"step": 2250
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.8406148867313916,
|
| 699 |
+
"grad_norm": 2.291496515274048,
|
| 700 |
+
"learning_rate": 1.3090169943749475e-05,
|
| 701 |
+
"loss": 0.14622759819030762,
|
| 702 |
+
"step": 2275
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.86084142394822,
|
| 706 |
+
"grad_norm": 0.38880622386932373,
|
| 707 |
+
"learning_rate": 1.2921841635218082e-05,
|
| 708 |
+
"loss": 0.14002437591552735,
|
| 709 |
+
"step": 2300
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.8810679611650487,
|
| 713 |
+
"grad_norm": 0.3293047249317169,
|
| 714 |
+
"learning_rate": 1.275260319310205e-05,
|
| 715 |
+
"loss": 0.21583776473999022,
|
| 716 |
+
"step": 2325
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.9012944983818771,
|
| 720 |
+
"grad_norm": 0.16572241485118866,
|
| 721 |
+
"learning_rate": 1.2582507334012755e-05,
|
| 722 |
+
"loss": 0.17850372314453125,
|
| 723 |
+
"step": 2350
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.9215210355987056,
|
| 727 |
+
"grad_norm": 4.988359451293945,
|
| 728 |
+
"learning_rate": 1.2411607041641062e-05,
|
| 729 |
+
"loss": 0.16260711669921876,
|
| 730 |
+
"step": 2375
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.941747572815534,
|
| 734 |
+
"grad_norm": 1.0162508487701416,
|
| 735 |
+
"learning_rate": 1.2239955550253277e-05,
|
| 736 |
+
"loss": 0.20481142044067382,
|
| 737 |
+
"step": 2400
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.9619741100323624,
|
| 741 |
+
"grad_norm": 0.41159898042678833,
|
| 742 |
+
"learning_rate": 1.2067606328109038e-05,
|
| 743 |
+
"loss": 0.12820093154907228,
|
| 744 |
+
"step": 2425
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.9822006472491909,
|
| 748 |
+
"grad_norm": 6.16225528717041,
|
| 749 |
+
"learning_rate": 1.1894613060806312e-05,
|
| 750 |
+
"loss": 0.18930299758911132,
|
| 751 |
+
"step": 2450
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.0024271844660193,
|
| 755 |
+
"grad_norm": 1.239059329032898,
|
| 756 |
+
"learning_rate": 1.172102963455871e-05,
|
| 757 |
+
"loss": 0.11151561737060547,
|
| 758 |
+
"step": 2475
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.0226537216828477,
|
| 762 |
+
"grad_norm": 0.14050441980361938,
|
| 763 |
+
"learning_rate": 1.1546910119410297e-05,
|
| 764 |
+
"loss": 0.07747174263000488,
|
| 765 |
+
"step": 2500
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.0226537216828477,
|
| 769 |
+
"eval_accuracy": 0.966144517433047,
|
| 770 |
+
"eval_f1": 0.977938755350675,
|
| 771 |
+
"eval_loss": 0.17465205490589142,
|
| 772 |
+
"eval_precision": 0.9712230215827338,
|
| 773 |
+
"eval_recall": 0.9847480106100795,
|
| 774 |
+
"eval_runtime": 34.5204,
|
| 775 |
+
"eval_samples_per_second": 57.328,
|
| 776 |
+
"eval_steps_per_second": 3.592,
|
| 777 |
+
"step": 2500
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 2.042880258899676,
|
| 781 |
+
"grad_norm": 0.5169682502746582,
|
| 782 |
+
"learning_rate": 1.1372308752393144e-05,
|
| 783 |
+
"loss": 0.12494021415710449,
|
| 784 |
+
"step": 2525
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.063106796116505,
|
| 788 |
+
"grad_norm": 2.469010829925537,
|
| 789 |
+
"learning_rate": 1.1197279920632864e-05,
|
| 790 |
+
"loss": 0.17911155700683593,
|
| 791 |
+
"step": 2550
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.0833333333333335,
|
| 795 |
+
"grad_norm": 0.20758801698684692,
|
| 796 |
+
"learning_rate": 1.1021878144407408e-05,
|
| 797 |
+
"loss": 0.1611471939086914,
|
| 798 |
+
"step": 2575
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.103559870550162,
|
| 802 |
+
"grad_norm": 18.897438049316406,
|
| 803 |
+
"learning_rate": 1.0846158060164359e-05,
|
| 804 |
+
"loss": 0.09400986671447754,
|
| 805 |
+
"step": 2600
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 2.1237864077669903,
|
| 809 |
+
"grad_norm": 0.48710235953330994,
|
| 810 |
+
"learning_rate": 1.0670174403502051e-05,
|
| 811 |
+
"loss": 0.10660056114196777,
|
| 812 |
+
"step": 2625
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.144012944983819,
|
| 816 |
+
"grad_norm": 5.023293972015381,
|
| 817 |
+
"learning_rate": 1.0493981992119833e-05,
|
| 818 |
+
"loss": 0.09857481956481934,
|
| 819 |
+
"step": 2650
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.164239482200647,
|
| 823 |
+
"grad_norm": 0.3322446942329407,
|
| 824 |
+
"learning_rate": 1.03176357087427e-05,
|
| 825 |
+
"loss": 0.1647811508178711,
|
| 826 |
+
"step": 2675
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.1844660194174756,
|
| 830 |
+
"grad_norm": 33.930667877197266,
|
| 831 |
+
"learning_rate": 1.0141190484025722e-05,
|
| 832 |
+
"loss": 0.21691896438598632,
|
| 833 |
+
"step": 2700
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 2.204692556634304,
|
| 837 |
+
"grad_norm": 0.22541019320487976,
|
| 838 |
+
"learning_rate": 9.964701279443509e-06,
|
| 839 |
+
"loss": 0.20835105895996095,
|
| 840 |
+
"step": 2725
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.2249190938511325,
|
| 844 |
+
"grad_norm": 0.2086869329214096,
|
| 845 |
+
"learning_rate": 9.788223070170112e-06,
|
| 846 |
+
"loss": 0.1038576602935791,
|
| 847 |
+
"step": 2750
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 2.2451456310679614,
|
| 851 |
+
"grad_norm": 1.6252963542938232,
|
| 852 |
+
"learning_rate": 9.6118108279546e-06,
|
| 853 |
+
"loss": 0.1402608013153076,
|
| 854 |
+
"step": 2775
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.26537216828479,
|
| 858 |
+
"grad_norm": 1.1920742988586426,
|
| 859 |
+
"learning_rate": 9.435519503997767e-06,
|
| 860 |
+
"loss": 0.1478741455078125,
|
| 861 |
+
"step": 2800
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.2855987055016183,
|
| 865 |
+
"grad_norm": 0.6118252277374268,
|
| 866 |
+
"learning_rate": 9.259404011835203e-06,
|
| 867 |
+
"loss": 0.10929722785949707,
|
| 868 |
+
"step": 2825
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 2.3058252427184467,
|
| 872 |
+
"grad_norm": 0.16680538654327393,
|
| 873 |
+
"learning_rate": 9.083519210232096e-06,
|
| 874 |
+
"loss": 0.11905492782592773,
|
| 875 |
+
"step": 2850
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 2.326051779935275,
|
| 879 |
+
"grad_norm": 0.19600656628608704,
|
| 880 |
+
"learning_rate": 8.907919886095115e-06,
|
| 881 |
+
"loss": 0.08101269721984863,
|
| 882 |
+
"step": 2875
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 2.3462783171521036,
|
| 886 |
+
"grad_norm": 1.6680601835250854,
|
| 887 |
+
"learning_rate": 8.732660737406663e-06,
|
| 888 |
+
"loss": 0.09864620208740234,
|
| 889 |
+
"step": 2900
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 2.366504854368932,
|
| 893 |
+
"grad_norm": 0.5449312925338745,
|
| 894 |
+
"learning_rate": 8.557796356186818e-06,
|
| 895 |
+
"loss": 0.16998577117919922,
|
| 896 |
+
"step": 2925
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.3867313915857604,
|
| 900 |
+
"grad_norm": 0.10003538429737091,
|
| 901 |
+
"learning_rate": 8.383381211488321e-06,
|
| 902 |
+
"loss": 0.23032936096191406,
|
| 903 |
+
"step": 2950
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 2.406957928802589,
|
| 907 |
+
"grad_norm": 7.103508472442627,
|
| 908 |
+
"learning_rate": 8.209469632429811e-06,
|
| 909 |
+
"loss": 0.08545310974121094,
|
| 910 |
+
"step": 2975
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 2.4271844660194173,
|
| 914 |
+
"grad_norm": 6.692376136779785,
|
| 915 |
+
"learning_rate": 8.036115791272697e-06,
|
| 916 |
+
"loss": 0.2049958038330078,
|
| 917 |
+
"step": 3000
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 2.4271844660194173,
|
| 921 |
+
"eval_accuracy": 0.9631126831733199,
|
| 922 |
+
"eval_f1": 0.9761047463175123,
|
| 923 |
+
"eval_loss": 0.1759410947561264,
|
| 924 |
+
"eval_precision": 0.9638009049773756,
|
| 925 |
+
"eval_recall": 0.9887267904509284,
|
| 926 |
+
"eval_runtime": 34.2085,
|
| 927 |
+
"eval_samples_per_second": 57.851,
|
| 928 |
+
"eval_steps_per_second": 3.625,
|
| 929 |
+
"step": 3000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.4474110032362457,
|
| 933 |
+
"grad_norm": 11.302281379699707,
|
| 934 |
+
"learning_rate": 7.863373686546868e-06,
|
| 935 |
+
"loss": 0.21097312927246092,
|
| 936 |
+
"step": 3025
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.4676375404530746,
|
| 940 |
+
"grad_norm": 5.9209113121032715,
|
| 941 |
+
"learning_rate": 7.691297126230515e-06,
|
| 942 |
+
"loss": 0.12400970458984376,
|
| 943 |
+
"step": 3050
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.487864077669903,
|
| 947 |
+
"grad_norm": 15.600579261779785,
|
| 948 |
+
"learning_rate": 7.519939710989326e-06,
|
| 949 |
+
"loss": 0.20074039459228515,
|
| 950 |
+
"step": 3075
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.5080906148867315,
|
| 954 |
+
"grad_norm": 14.571202278137207,
|
| 955 |
+
"learning_rate": 7.349354817480234e-06,
|
| 956 |
+
"loss": 0.0825264072418213,
|
| 957 |
+
"step": 3100
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.52831715210356,
|
| 961 |
+
"grad_norm": 0.2681007981300354,
|
| 962 |
+
"learning_rate": 7.179595581724971e-06,
|
| 963 |
+
"loss": 0.13173922538757324,
|
| 964 |
+
"step": 3125
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.5485436893203883,
|
| 968 |
+
"grad_norm": 0.1719094216823578,
|
| 969 |
+
"learning_rate": 7.010714882558551e-06,
|
| 970 |
+
"loss": 0.09000961303710937,
|
| 971 |
+
"step": 3150
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.5687702265372168,
|
| 975 |
+
"grad_norm": 0.06844039261341095,
|
| 976 |
+
"learning_rate": 6.842765325157874e-06,
|
| 977 |
+
"loss": 0.13644008636474608,
|
| 978 |
+
"step": 3175
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.588996763754045,
|
| 982 |
+
"grad_norm": 11.590834617614746,
|
| 983 |
+
"learning_rate": 6.675799224655588e-06,
|
| 984 |
+
"loss": 0.07055030345916748,
|
| 985 |
+
"step": 3200
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.6092233009708736,
|
| 989 |
+
"grad_norm": 0.16210342943668365,
|
| 990 |
+
"learning_rate": 6.509868589844274e-06,
|
| 991 |
+
"loss": 0.10780407905578614,
|
| 992 |
+
"step": 3225
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.6294498381877025,
|
| 996 |
+
"grad_norm": 0.1514226347208023,
|
| 997 |
+
"learning_rate": 6.34502510697607e-06,
|
| 998 |
+
"loss": 0.06451849937438965,
|
| 999 |
+
"step": 3250
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.649676375404531,
|
| 1003 |
+
"grad_norm": 0.14009274542331696,
|
| 1004 |
+
"learning_rate": 6.181320123662755e-06,
|
| 1005 |
+
"loss": 0.13269135475158692,
|
| 1006 |
+
"step": 3275
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.6699029126213594,
|
| 1010 |
+
"grad_norm": 1.227739930152893,
|
| 1011 |
+
"learning_rate": 6.018804632881326e-06,
|
| 1012 |
+
"loss": 0.1452858829498291,
|
| 1013 |
+
"step": 3300
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.690129449838188,
|
| 1017 |
+
"grad_norm": 0.12412651628255844,
|
| 1018 |
+
"learning_rate": 5.857529257090027e-06,
|
| 1019 |
+
"loss": 0.11763744354248047,
|
| 1020 |
+
"step": 3325
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.7103559870550162,
|
| 1024 |
+
"grad_norm": 9.471817016601562,
|
| 1025 |
+
"learning_rate": 5.6975442324598165e-06,
|
| 1026 |
+
"loss": 0.10433626174926758,
|
| 1027 |
+
"step": 3350
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.7305825242718447,
|
| 1031 |
+
"grad_norm": 5.368896961212158,
|
| 1032 |
+
"learning_rate": 5.538899393226122e-06,
|
| 1033 |
+
"loss": 0.14967796325683594,
|
| 1034 |
+
"step": 3375
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.750809061488673,
|
| 1038 |
+
"grad_norm": 0.7815220355987549,
|
| 1039 |
+
"learning_rate": 5.381644156165844e-06,
|
| 1040 |
+
"loss": 0.13424870491027832,
|
| 1041 |
+
"step": 3400
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.7710355987055015,
|
| 1045 |
+
"grad_norm": 17.132827758789062,
|
| 1046 |
+
"learning_rate": 5.225827505204355e-06,
|
| 1047 |
+
"loss": 0.12580464363098146,
|
| 1048 |
+
"step": 3425
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 2.79126213592233,
|
| 1052 |
+
"grad_norm": 2.3049182891845703,
|
| 1053 |
+
"learning_rate": 5.071497976157346e-06,
|
| 1054 |
+
"loss": 0.18594202041625976,
|
| 1055 |
+
"step": 3450
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.8114886731391584,
|
| 1059 |
+
"grad_norm": 9.519274711608887,
|
| 1060 |
+
"learning_rate": 4.918703641612255e-06,
|
| 1061 |
+
"loss": 0.14881797790527343,
|
| 1062 |
+
"step": 3475
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.831715210355987,
|
| 1066 |
+
"grad_norm": 7.568735599517822,
|
| 1067 |
+
"learning_rate": 4.767492095953985e-06,
|
| 1068 |
+
"loss": 0.10424537658691406,
|
| 1069 |
+
"step": 3500
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.831715210355987,
|
| 1073 |
+
"eval_accuracy": 0.9676604345629105,
|
| 1074 |
+
"eval_f1": 0.9789335088874259,
|
| 1075 |
+
"eval_loss": 0.1581990271806717,
|
| 1076 |
+
"eval_precision": 0.9718954248366013,
|
| 1077 |
+
"eval_recall": 0.9860742705570292,
|
| 1078 |
+
"eval_runtime": 34.2504,
|
| 1079 |
+
"eval_samples_per_second": 57.78,
|
| 1080 |
+
"eval_steps_per_second": 3.62,
|
| 1081 |
+
"step": 3500
|
| 1082 |
+
}
|
| 1083 |
+
],
|
| 1084 |
+
"logging_steps": 25,
|
| 1085 |
+
"max_steps": 4944,
|
| 1086 |
+
"num_input_tokens_seen": 0,
|
| 1087 |
+
"num_train_epochs": 4,
|
| 1088 |
+
"save_steps": 500,
|
| 1089 |
+
"stateful_callbacks": {
|
| 1090 |
+
"EarlyStoppingCallback": {
|
| 1091 |
+
"args": {
|
| 1092 |
+
"early_stopping_patience": 2,
|
| 1093 |
+
"early_stopping_threshold": 0.0
|
| 1094 |
+
},
|
| 1095 |
+
"attributes": {
|
| 1096 |
+
"early_stopping_patience_counter": 0
|
| 1097 |
+
}
|
| 1098 |
+
},
|
| 1099 |
+
"TrainerControl": {
|
| 1100 |
+
"args": {
|
| 1101 |
+
"should_epoch_stop": false,
|
| 1102 |
+
"should_evaluate": false,
|
| 1103 |
+
"should_log": false,
|
| 1104 |
+
"should_save": true,
|
| 1105 |
+
"should_training_stop": false
|
| 1106 |
+
},
|
| 1107 |
+
"attributes": {}
|
| 1108 |
+
}
|
| 1109 |
+
},
|
| 1110 |
+
"total_flos": 1.472790443483136e+16,
|
| 1111 |
+
"train_batch_size": 16,
|
| 1112 |
+
"trial_name": null,
|
| 1113 |
+
"trial_params": null
|
| 1114 |
+
}
|
checkpoint-3500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6356dffa425669d6696f329ab57522ceda02ab7fadb057794c10a172cb56de1f
|
| 3 |
+
size 5201
|